print("📊 Analysis Methodology:")
print("=" * 40)
print("1. Exploratory Data Analysis (EDA)")
print("   - Data profiling and quality assessment")
print("   - Descriptive statistics and distributions")
print("   - Missing value and outlier detection")
print()
print("2. Statistical Testing & Inference")
print("   - Correlation analysis between key variables")
print("   - T-tests for demographic differences")
print("   - Distribution analysis (skewness, kurtosis)")
print()
print("3. Advanced Analytics")
print("   - Customer segmentation analysis")
print("   - Behavioral pattern identification")
print("   - Risk assessment and satisfaction analysis")
print()
print("4. Business Intelligence")
print("   - Interactive visualizations (Plotly)")
print("   - Statistical plots (Seaborn, Matplotlib)")
print("   - Data-driven recommendations")
print()
print("5. Tools & Technologies")
print("   - Python: Pandas, NumPy, Scipy")
print("   - Visualization: Plotly, Seaborn, Matplotlib")
print("   - Statistical Analysis: Hypothesis testing, correlation")

# Import libraries and load data
import os
import pandas as pd
import numpy as np
import plotly.express as px
import seaborn as sns
import matplotlib.pyplot as plt
from scipy.stats import ttest_ind, skew, kurtosis

# Load the cleaned dataset
merged_data_filename = os.path.join("..", "data", "processed", "Credit_Card_Financial.csv")
merged_df = pd.read_csv(merged_data_filename)

# Check for missing values
missing_values = merged_df.isnull().sum()
print("Missing Values Summary:")
print(missing_values[missing_values > 0] if missing_values.sum() > 0 else "No missing values found")

# Basic dataset info
print(f"\nDataset Info:")
print(f"Shape: {merged_df.shape}")
print(f"Memory Usage: {merged_df.memory_usage(deep=True).sum() / 1024**2:.2f} MB")

# Calculate correlations for key financial variables
corr_vars = ['Income', 'Credit_Limit', 'Total_Trans_Amt', 'Annual_Fees']
corr_matrix = merged_df[corr_vars].corr()

print("Key Correlation Coefficients:")
print(f"Income vs Total_Trans_Amt: {corr_matrix.loc['Income', 'Total_Trans_Amt']:.3f}")
print(f"Income vs Credit_Limit: {corr_matrix.loc['Income', 'Credit_Limit']:.3f}")
print(f"Credit_Limit vs Total_Trans_Amt: {corr_matrix.loc['Credit_Limit', 'Total_Trans_Amt']:.3f}")

# Calculate correlations for key financial variables
corr_vars = ['Income', 'Credit_Limit', 'Total_Trans_Amt', 'Annual_Fees']
corr_matrix = merged_df[corr_vars].corr()

# Create the heatmap
plt.figure(figsize=(5, 4))
sns.heatmap(corr_matrix, annot=True, cmap='Blues', center=0, 
            square=True, linewidths=0.5, cbar_kws={"shrink": .8})
plt.title("Correlation Matrix of Key Financial Variables")
plt.tight_layout()
plt.show()

# Calculate skewness and kurtosis
credit_limit_skew = skew(merged_df["Credit_Limit"].dropna())
credit_limit_kurt = kurtosis(merged_df["Credit_Limit"].dropna())

print("Credit Limit Distribution Analysis:")
print(f"Skewness: {credit_limit_skew:.3f} (Right-skewed if > 0)")
print(f"Kurtosis: {credit_limit_kurt:.3f} (Heavy tails if > 0)")
print(f"Mean: ${merged_df['Credit_Limit'].mean():,.0f}")
print(f"Median: ${merged_df['Credit_Limit'].median():,.0f}")

gender_dist = merged_df['Gender'].value_counts().reset_index()
gender_dist.columns = ['Gender', 'Count']

fig = px.pie(gender_dist, names='Gender', values='Count', 
             title="Gender Distribution",
             color_discrete_sequence=["#003399", "#3366cc"])

fig.update_traces(texttemplate="%{percent:.1%}", textposition="inside")
fig.update_layout(showlegend=True, margin=dict(l=60, r=50, t=50, b=150))
fig.show()

income_by_education = merged_df.groupby('Education_Level')['Income'].mean().reset_index()
income_by_education = income_by_education.sort_values('Income', ascending=False)

fig = px.bar(income_by_education, x='Education_Level', y='Income',
             title='Average Income by Education Level',
             color_discrete_sequence=['#002366'])

fig.update_layout(xaxis_title="Education Level", yaxis_title="Average Income ($)", 
                 bargap=0.4, bargroupgap=0.2, margin=dict(l=60, r=50, t=50, b=150))
fig.show()

credit_by_card = merged_df.groupby('Card_Category')['Credit_Limit'].mean().reset_index()
credit_by_card = credit_by_card.sort_values('Credit_Limit', ascending=False)

fig = px.bar(credit_by_card, x='Card_Category', y='Credit_Limit',
             title='Average Credit Limit by Card Type',
             color_discrete_sequence=['#002366'])

fig.update_layout(xaxis_title="Card Type", yaxis_title="Average Credit Limit ($)", 
                 bargap=0.4, bargroupgap=0.2, margin=dict(l=60, r=50, t=50, b=150))
fig.show()

# Perform t-test
men_credit = merged_df[merged_df['Gender'] == 'Male']['Credit_Limit']
women_credit = merged_df[merged_df['Gender'] == 'Female']['Credit_Limit']

t_stat, p_value = ttest_ind(men_credit, women_credit, nan_policy='omit')

print("T-Test Results: Gender vs Credit Limit")
print(f"T-statistic: {t_stat:.3f}")
print(f"P-value: {p_value:.6f}")
print(f"Significant difference: {'Yes' if p_value < 0.05 else 'No'}")
print(f"Male average Credit Limit: ${men_credit.mean():,.0f}")
print(f"Female average Credit Limit: ${women_credit.mean():,.0f}")

# Create month order for proper sorting
month_order = ['January', 'February', 'March', 'April', 'May', 'June',
               'July', 'August', 'September', 'October', 'November', 'December']

# Group by month and calculate total transactions
monthly_trans = merged_df.groupby('Month')['Total_Trans_Amt'].sum().reset_index()
monthly_trans['Month'] = pd.Categorical(monthly_trans['Month'], categories=month_order, ordered=True)
monthly_trans = monthly_trans.sort_values('Month')

fig = px.line(monthly_trans, x='Month', y='Total_Trans_Amt',
              title='Total Transaction Amount Over Time',
              markers=True)

fig.update_traces(line_shape='spline', line=dict(color='#002366', width=3))
fig.update_layout(xaxis_title="Month", yaxis_title="Total Transaction Amount ($)", 
                 margin=dict(l=80, r=30, t=50, b=150))
fig.show()

delinq_by_state = merged_df.groupby('state_cd')['Delinquent_Acc'].sum().reset_index()
delinq_by_state = delinq_by_state.sort_values('Delinquent_Acc', ascending=False).head(10)

fig = px.bar(delinq_by_state, x='Delinquent_Acc', y='state_cd',
             orientation='h',
             title='Top 10 States with Highest Delinquent Accounts',
             color_discrete_sequence=['#002366'])

fig.update_layout(xaxis_title="Number of Delinquent Accounts", yaxis_title="State", 
                 margin=dict(l=150, r=50, t=50, b=150))
fig.show()

satisfaction_dist = merged_df.groupby('Cust_Satisfaction_Score')['Client_Num'].count().reset_index()
satisfaction_dist.columns = ['Satisfaction_Score', 'Customer_Count']

fig = px.bar(satisfaction_dist, x='Satisfaction_Score', y='Customer_Count',
             title='Customer Count by Satisfaction Level',
             color_discrete_sequence=['#002366'])

fig.update_layout(xaxis_title="Satisfaction Score", yaxis_title="Number of Customers", 
                 bargap=0.4, bargroupgap=0.2, margin=dict(l=80, r=50, t=50, b=150))
fig.show()